CPSC 503 Computational Linguistics

1. CPSC 503Computational Linguistics Lecture 12 Giuseppe Carenini CPSC503 Winter 2008

2. Semantic Analysis Sentence Meanings of grammatical structures Syntax-driven Semantic Analysis Meanings of words Literal Meaning I N F E R E N C E Common-Sense Domain knowledge Further Analysis Discourse Structure Intended meaning Context CPSC503 Winter 2008

3. PropNoun -> AyCaramba MassNoun -> meat Attachments {AyCaramba} {MEAT} lambda-form • Verb -> serves Word Meaning in Syntax-driven SA assigning constants NLTK book: Chp11. Logical Semantics (90% complete) CPSC503 Winter 2008

4. Today 20/10 • How much it is missed by this narrow view! • Relations among words and their meanings • Internal structure of individual words CPSC503 Winter 2008

5. Word Meaning Theory • Paradigmatic: the external relational structure among words • Syntagmatic: the internal structure of words that determines how they can be combined with other words CPSC503 Winter 2008

6. Stem? Word? Lemma? Lexeme: • Orthographic form + • Phonological form + • symbolic Meaning representation (sense) content? duck? bank? • Lexicon: A collection of lexemes CPSC503 Winter 2008

7. Dictionary Repositories of information about the meaning of words, but….. • Most of the definitions are circular… ?? They are descriptions…. • Fortunately, there is still some useful semantic info (Lexical Relations): • L1,L2 same O and P, different M • L1,L2 “same” M, different O • L1,L2 “opposite” M • L1,L2 , M1 subclass of M1 Homonymy Synonymy Antonymy Hyponymy CPSC503 Winter 2008

8. Homographs Homonyms Homophones content/content wood/would Homonymy Def. Lexemes that have the same “forms” but unrelated meanings • Examples: Bat (wooden stick-like thing) vs. Bat (flying scary mammal thing) • Plant (…….) vs. • Plant (………) CPSC503 Winter 2008

9. Homonymy: NLP Tasks • Information retrieval: • QUERY: bat • Spelling correction: homophones can lead to real-word spelling errors • Text-to-Speech: Homographs (which are not homophones) CPSC503 Winter 2008

10. Polysemy Def. The case where we have a set of lexemes with the same form and multiple related meanings. Consider the homonym: bank  commercial bank1 vs. river bank2 • Now consider: “A PCFG can be trained using derivation trees from a tree bank annotated by human experts” • Is this a new independent sense of bank? CPSC503 Winter 2008

11. Polysemy • Lexeme (new def.): • Orthographic form + Phonological form + • Set of related senses • How many distinct (but related) senses? • They serve meat… • He served as Dept. Head… • She served her time…. Different subcat Intuition (prison) • Does AC serve vegetarian food? • Does AC serve Rome? • (?)Does AC serve vegetarian food and Rome? Zeugma CPSC503 Winter 2008

12. Synonyms • Def. Different lexemes with the same meaning. Would I be flying on a large/big plane? • Substitutability- if they can be substituted for one another in some environment without changing meaning or acceptability. ?… became kind of a large/big sister to… ? You made a large/big mistake CPSC503 Winter 2008

13. Hyponymy • Def. Pairings where one lexeme denotes a subclass of the other • Since dogs are canids • Dogis a hyponym of canid and • Canid is a hypernymof dog • car/vehicle • doctor/human CPSC503 Winter 2008

14. Lexical Resources • Databases containing all lexical relations among all lexemes • Development: • Mining info from dictionaries and thesauri • Handcrafting it from scratch • WordNet: most well-developed and widely used [Fellbaum… 1998] • for English (versions for other languages have been developed – see MultiWordNet) CPSC503 Winter 2008

15. WordNet 3.0 • For each lemma: all possible senses (no distinction between homonymy and polysemy) • For each sense: a set of synonyms (synset) and a gloss CPSC503 Winter 2008

16. WordNet: table entry The noun "table" has 6 senses in WordNet.1. table, tabular array -- (a set of data …)2. table -- (a piece of furniture …)3. table -- (a piece of furniture with tableware…)4. mesa, table -- (flat tableland …)5. table -- (a company of people …)6. board, table -- (food or meals …) The verb "table" has 1 sense in WordNet.1. postpone, prorogue, hold over, put over, table, shelve, set back, defer, remit, put off – (hold back to a later time; "let's postpone the exam") CPSC503 Winter 2008

17. WordNet Relations fi CPSC503 Winter 2008

18. WordNet Hierarchies: example WordNet: example from ver1.7.1 Sense 3: Vancouver (city, metropolis, urban center)  (municipality)  (urban area)  (geographical area)  (region)  (location)  (entity, physical thing)  (administrative district, territorial division)  (district, territory)  (region)  (location  (entity, physical thing)  (port)  (geographic point)  (point)  (location)  (entity, physical thing) CPSC503 Winter 2008

19. Wordnet: NLP Tasks • Probabilistic Parsing (PP-attachments): words + word-classes extracted from the hypernym hierarchy increase accuracy from 84% to 88% [Stetina and Nagao, 1997] • Word sense disambiguation (next class) • Lexical Chains (summarization) • Express Selectional Preferences for verbs • ……… CPSC503 Winter 2008

20. Today Outline • How much it is missed by this narrow view! • Relations among words and their meanings • Internal structure of individual words CPSC503 Winter 2008

21. Predicate-Argument Structure • Represent relationships among concepts • Some words act like arguments and some words act like predicates: • Nouns as concepts or arguments: red(ball) • Adj, Adv, Verbs as predicates: red(ball) “I ate a turkey sandwich for lunch” $w: Isa(w,Eating) ÙEater(w,Speaker) Ù Eaten(w,TurkeySandwich) Ù MealEaten(w,Lunch) “AyCaramba serves meat” $w: Isa(w,Serving) ÙServer(w,Speaker) Ù Served(w,Meat) CPSC503 Winter 2008

22. Semantic Roles • Def. Semantic generalizations over the specific roles that occur with specific verbs. • I.e. eaters, servers, takers, givers, makers, doers, killers, all have something in common • We can generalize (or try to) across other roles as well CPSC503 Winter 2008

23. Constraint Generation Support “more abstract” INFERENCE Thematic Roles: Usage Sentence Syntax-driven Semantic Analysis Eg. Instrument “with” Literal Meaning expressed with thematic roles Eg. Subject? Further Analysis Eg. Result did not exist before Intended meaning CPSC503 Winter 2008

24. Thematic Role Examples fi fl CPSC503 Winter 2008

25. Thematic Roles fi fi • Not definitive, not from a single theory! CPSC503 Winter 2008

26. Problem with Thematic Roles • NO agreement of what should be the standard set • NO agreement on formal definition • Fragmentation problem: when you try to formally define a role you end up creating more specific sub-roles • Two solutions • Generalized semantic roles • Define verb (or class of verbs) specific semantic roles CPSC503 Winter 2008

27. Generalized Semantic Roles • Very abstract roles are defined heuristically as a set of conditions • The more conditions are satisfied the more likely an argument fulfills that role • Proto-Patient • Undergoes change of state • Incremental theme • Causally affected by another participant • Stationary relative to movement of another participant • (does not exist independently of the event, or at all) • Proto-Agent • Volitional involvement in event or state • Sentience (and/or perception) • Causing an event or change of state in another participant • Movement (relative to position of another participant) • (exists independently of event named) CPSC503 Winter 2008

28. Semantic Roles: Resources • Databases containing for each verb its syntactic and thematic argument structures • PropBank: sentences in the Penn Treebank annotated with semantic roles • Roles are verb-sense specific • Arg0 (PROTO-AGENT), Arg1(PROTO-PATIENT), Arg2,……. • (see also VerbNet) CPSC503 Winter 2008

29. PropBank Example • Increase “go up incrementally” • Arg0: causer of increase • Arg1: thing increasing • Arg2: amount increase by • Arg3: start point • Arg4: end point • PropBank semantic role labeling would identify common aspects among these three examples • “ Y performance increased by 3% ” • “ Y performance was increased by the new X technique ” • “ The new X technique increased performance of Y” CPSC503 Winter 2008

30. Semantic Roles: Resources • Move beyond inferences aboutsingle verbs “ IBM hired John as a CEO ” “ John is the new IBM hire ” “ IBM signed John for 2M$” • FrameNet: Databases containing frames and their syntactic and semantic argument structures • (book online Version 1.3 Printed August 25, 2006) • for English (versions for other languages are under development) CPSC503 Winter 2008

31. FrameNet Entry • Hiring • Definition: An Employer hires an Employee, promising the Employee a certain Compensation in exchange for the performance of a job. The job may be described either in terms of a Task or a Position in a Field. • Inherits From: Intentionally affect • Lexical Units: commission.n, commission.v, give job.v, hire.n, hire.v, retain.v, sign.v, take on.v CPSC503 Winter 2008

32. FrameNet Annotations Some roles.. Employer Employee Task Position • np-vpto • In 1979 , singer Nancy Wilson HIRED himto open her nightclub act . • …. • np-ppas • Castro has swallowed his doubts and HIRED Valenzuela as a cook in his small restaurant . Includes counting: How many times a role was expressed with a particular syntactic structure… CPSC503 Winter 2008

33. Summary • Relations among words and their meanings Wordnet • Internal structure of individual words PropBank FrameNet CPSC503 Winter 2008

34. Next Time Read Chp. 20 Computational Lexical Semantics • Word Sense Disambiguation • Word Similarity • Semantic Role Labeling CPSC503 Winter 2008